How to integrate Mem0 MCP with OpenAI Agents SDK

This guide walks you through connecting Mem0 to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Mem0 agent that can store meeting notes from today's call, export all project memories as csv, add new user to our team space through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Mem0 account through Composio's Mem0 MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Mem0 logoMem0
Api Key

Mem0 is an AI-powered note-taking and knowledge management platform. It helps you organize, search, and generate content from your personal knowledge base.

47 Tools

Introduction

This guide walks you through connecting Mem0 to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Mem0 agent that can store meeting notes from today's call, export all project memories as csv, add new user to our team space through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Mem0 account through Composio's Mem0 MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Mem0 with

ChatGPTClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Mem0
  • Configure an AI agent that can use Mem0 as a tool
  • Run a live chat session where you can ask the agent to perform Mem0 operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Mem0 MCP server, and what's possible with it?

The Mem0 MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mem0 account. It provides structured and secure access to your notes, projects, and organizational knowledge, so your agent can perform actions like searching memories, managing users, adding content, and orchestrating agent runs on your behalf.

  • AI-powered memory search and recall: Let your agent search and retrieve existing memory entries using advanced filters and pagination to surface just the right note or piece of information.
  • Automated content and note creation: Have your agent store new memory records from conversations, meetings, or tasks—ensuring nothing slips through the cracks.
  • Collaboration and organization management: Direct your agent to add members to projects or organizations, assign roles, and keep team structures up to date.
  • Agent and application orchestration: Enable your agent to create new AI agents, initiate agent runs, and manage applications for custom workflows and automation.
  • Structured knowledge export and reporting: Ask your agent to initiate export jobs with specific schemas and filters, so you can back up or analyze your stored knowledge on demand.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Mem0 project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Mem0.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Mem0
const session = await composio.create(userId as string, {
  toolkits: ['mem0'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only mem0.
  • The router checks the user's Mem0 connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Mem0.
  • This approach keeps things lightweight and lets the agent request Mem0 tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Mem0. Help users perform Mem0 operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Mem0 and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Mem0 operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Mem0.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Mem0 and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['mem0'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Mem0. Help users perform Mem0 operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Mem0 MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Mem0.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

Every Mem0 action and event your agent gets out of the box.

Add member to project

Adds an existing user to a project (identified by `project_id` within organization `org_id`), assigning a valid system role.

Add new memory records

Stores new memory records from a list of messages, optionally inferring structured content; requires association via `agent_id`, `user_id`, `app_id`, or `run_id`.

Add organization member

Adds a new member, who must be a registered user, to an organization, assigning them a specific role.

Create a new agent

Creates a new agent with a unique `agent_id` and an optional `name`; additional metadata may be assigned by the system.

Create a new agent run

Creates a new agent run in the mem0.

Create a new application

Creates a new application, allowing metadata to be passed in the request body (not an explicit field in this action's request model); ensure `app_id` is unique to avoid potential errors or unintended updates.

Create a new organization entry

Creates a new organization entry using the provided name and returns its details.

Create a new user

Creates a new user with the specified unique `user_id` and supports associating `metadata` (not part of the request schema fields).

Create memory entry

Lists/searches existing memory entries with filtering and pagination; critically, this action retrieves memories and does *not* create new ones, despite its name.

Create project

Creates a new project with a given name within an organization that must already exist.

Create webhook

Creates a new webhook for a specific project to receive real-time notifications.

Delete an organization

Permanently deletes an existing organization identified by its unique ID.

Delete memory by id

Permanently deletes a specific memory by its unique ID; ensure the `memory_id` exists as this operation is irreversible.

Delete entity by type and id

Call to permanently and irreversibly hard-delete an existing entity (user, agent, app, or run) and all its associated data, using its type and ID.

Delete memories

Deletes all memories matching specified filter criteria.

Delete memory batch with uuids

Deletes a batch of up to 1000 existing memories, identified by their UUIDs, in a single API call.

Delete project

Permanently deletes a specific project and all its associated data from an organization; this action cannot be undone and requires the project to exist within the specified organization.

Delete project member

Removes an existing member, specified by email address, from a project, immediately revoking their project-specific access; the user is not removed from the organization.

Delete webhook

Deletes a webhook and stops receiving notifications for the specified webhook ID.

Export data based on filters

Creates a new memory export job with optional entity filters (user_id, agent_id, app_id, run_id).

List organizations

Retrieves a summary list of organizations for administrative oversight; returns summary data (names, IDs), not exhaustive details, despite 'detailed' in the name.

Fetch details of a specific organization

Fetches comprehensive details for an organization using its `org_id`; the `org_id` must be valid and for an existing organization.

Get list of entity filters

Retrieves predefined filter definitions for entities (e.

Get entity by id

Fetches detailed information for an existing entity (user, agent, app, or run) identified by its type and unique ID.

Get event status by event ID

Retrieves a single async event by ID to check its current status and results.

Get memories by entity

Tool to retrieve all memories associated with a specific entity (user, agent, app, or run).

Get memory export

Retrieves the status and results of a memory export job by its ID.

Get organization members

Fetches a list of members for a specified, existing organization.

Get project details

Fetches comprehensive details for a specified project within an organization.

Get project members

Retrieves all members for a specified project within an organization.

Get projects

Retrieves all projects for a given organization `org_id` to which the caller has access.

Get project webhooks

Retrieves all webhooks configured for a specific project.

Get user memory stats

Retrieves a summary of the authenticated user's memory activity, including total memories created, search events, and add events.

List entities

Retrieves a list of entities, optionally filtered by organization or project (prefer `org_id`/`project_id` over deprecated `org_name`/`project_name`), noting results may be summaries and subject to limits.

Perform semantic search on memories

Searches memories semantically using a natural language query and metadata filters.

Remove a member from the organization

Removes a member, specified by their username, from an existing organization of which they are currently a member.

Retrieve all events for the currently logged in user

Retrieves a paginated list of events for the authenticated user, filterable and paginable via URL query parameters.

Retrieve list of memory events

Retrieves a chronological list of all memory events (e.

Retrieve memory by id

Retrieves a complete memory entry by its unique identifier; `memory_id` must be valid and for an existing memory.

Retrieve memory history by id

Retrieves the complete version history for an existing memory, using its unique `memory_id`, to inspect its evolution or audit changes.

Retrieve memory list

Retrieves a list of memories, supporting pagination and diverse filtering (e.

Search memories with filters

Semantically searches memories using structured filters with an optional natural language query.

Update memory batch with uuid

Updates text for up to 1000 memories in a single batch, using their UUIDs.

Update memory text content

Updates the text content of an existing memory, identified by its `memory_id`.

Update organization member role

Updates the role of an existing member to a new valid role within an existing organization.

Update project

Updates a project by `project_id` within an `org_id`, modifying only provided fields (name, description, custom_instructions, custom_categories); list fields are fully replaced (cleared by `[]`), other omitted/null fields remain unchanged.

Update project member role

Updates the role of a specific member within a designated project, ensuring the new role is valid and recognized by the system.

FRAMEWORKS

How to build Mem0 MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Mem0 MCP with ChatGPT

Claude Agent SDK logo

Claude Agent SDK

Use Mem0 MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Mem0 MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Mem0 MCP with Claude Cowork

Codex logo

Codex

Use Mem0 MCP with Codex

Cursor logo

Cursor

Use Mem0 MCP with Cursor

OpenClaw logo

OpenClaw

Use Mem0 MCP with OpenClaw

Hermes logo

Hermes

Use Mem0 MCP with Hermes

CLI logo

CLI

Use Mem0 MCP with CLI

Google ADK logo

Google ADK

Use Mem0 MCP with Google ADK

LangChain logo

LangChain

Use Mem0 MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Mem0 MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Mem0 MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Mem0 MCP with LlamaIndex

CrewAI logo

CrewAI

Use Mem0 MCP with CrewAI

OpenCode logo

OpenCode

Use Mem0 MCP with OpenCode

VS Code logo

VS Code

Use Mem0 MCP with VS Code

FAQ

Frequently asked questions

With a standalone Mem0 MCP server, the agents and LLMs can only access a fixed set of Mem0 tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mem0 and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Mem0 tools.

Yes, absolutely. You can configure which Mem0 scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Mem0 data and credentials are handled as safely as possible.

Start with Mem0.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Mem0 tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies